Why in different execution different performance comes in the Neural Network same program ?
4 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
Deep Gogoi
el 8 de Mayo de 2015
Comentada: Greg Heath
el 14 de Mayo de 2015
Why in different execution different performance comes in the Neural Network same program ?
0 comentarios
Respuesta aceptada
Greg Heath
el 8 de Mayo de 2015
The state of the RNG is different. Therefore the random initial weights and random trn/val/tst data divisions are different.
For examples of initializing the RNG so that runs can be duplicated try searching on
greg rng(4151941)
greg rng(0)
greg rng('default')
4 comentarios
Greg Heath
el 14 de Mayo de 2015
You wouldn't have to post your data for me to do your work if you had performed the searches I recommended.
Más respuestas (0)
Ver también
Categorías
Más información sobre Classification en Help Center y File Exchange.
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!